© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59894
    Prev
    Next
    INDEX
    Explanations

    places or names followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly fires on programming‐style syntax—especially C# keywords (using, namespace, class, etc.), punctuation (.;//), and code constructs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewBag
    -0.85
    ITECH
    -0.82
    tilor
    -0.79
    ObservableList
    -0.77
    cps
    -0.76
     JComboBox
    -0.75
    Parcelable
    -0.75
    controller
    -0.74
    Islamic
    -0.73
    Widget
    -0.73
    POSITIVE LOGITS
     wineries
    0.80
     sydney
    0.79
     pug
    0.75
     washington
    0.75
    tiskt
    0.75
    seattle
    0.73
     WSU
    0.73
    VIOL
    0.73
     Puget
    0.73
    Washington
    0.72
    Activations Density 0.004%

    No Known Activations